Scribd
Upload
58 views

Introductory Econometrics: Prachi Singh & Partha Bandopadhyay

The document provides an introduction to an introductory econometrics course being taught by Prachi Singh and Partha Bandopadhyay at Ashoka University on January 20, 2021. It outlines the evaluation criteria, reference materials, topics to be covered including econometric modeling, data analysis in STATA, and reading journal articles. It also distinguishes between correlation and causation, and provides examples of cross-sectional and time series data.

Uploaded by

Gaurav Jakhu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
58 views

Introductory Econometrics: Prachi Singh & Partha Bandopadhyay

The document provides an introduction to an introductory econometrics course being taught by Prachi Singh and Partha Bandopadhyay at Ashoka University on January 20, 2021. It outlines the evaluation criteria, reference materials, topics to be covered including econometric modeling, data analysis in STATA, and reading journal articles. It also distinguishes between correlation and causation, and provides examples of cross-sectional and time series data.

Uploaded by

Gaurav Jakhu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 29

Introductory Econometrics

Prachi Singh & Partha Bandopadhyay

Ashoka University

January 20, 2021

Lecture 1 ECO-2400 January 20, 2021 1 / 29


Introduction

What you need

Understanding of basic statistics (course ECO-1400).


STATA: No worries if you haven’t used it before but make sure that
you put in extra effort to be comfortable as most of assessments are
going to have a STATA component as well.
Regularity

Lecture 1 ECO-2400 January 20, 2021 2 / 29


Introduction

Evaluation

Mid-term: 30 percent - 6th March, 2021


STATA Assignment 1: 10 percent - TBD
STATA Assignment 2: 10 percent - TBD
End-term: 50 percent - 5th May, 2021 (can change if the department
decides to conduct the exam of compulsory courses at the same time
for all sections)
IMPORTANT: If I catch you cheating (If your answers are eerily similar -
imagine similar errors, copy pasted material) then I will deduct 20 marks
and report you to OAA directly.
Your grades will be based on your ABSOLUTE marks, I will use OAA
grading cut-offs.

Lecture 1 ECO-2400 January 20, 2021 3 / 29


Introduction

Reference

Chapters 1 to 7: Introductory Econometrics - A Modern Approach by


Jeffrey M. Woolridge (5th edition)
STATA Introduction & Graphing: German Rodriguez’s website (see
link in CourseOutline.xlsx )
STATA miscellaneous: I will introduce more datasets in class to play
around. You will get some new random dataset for your assignments
and in your exams.
You will not get any problem sets. The exercises at the end of each
chapter of Woolridge should be used as sample exercises.

Lecture 1 ECO-2400 January 20, 2021 4 / 29


Introduction

No attendance but I will monitor your participation

Lecture 1 ECO-2400 January 20, 2021 5 / 29


Introduction

Your choice entirely

Lecture 1 ECO-2400 January 20, 2021 6 / 29


Introduction

What we will learn

Drawing inferences from a sample of a population.


Econometric Modelling.
Data analysis tools.
Coding in STATA

Lecture 1 ECO-2400 January 20, 2021 7 / 29


Introduction

Reading Journal Articles

Lecture 1 ECO-2400 January 20, 2021 8 / 29


Introduction

Creating graphs for data analysis

Lecture 1 ECO-2400 January 20, 2021 9 / 29


Introduction

What you will NOT learn

Building sophisticated models of CAUSALITY

Lecture 1 ECO-2400 January 20, 2021 10 / 29


Introduction

REMEMBER: Correlation does not IMPLY Causation

Lecture 1 ECO-2400 January 20, 2021 11 / 29


Introduction

Correlation

Relation between two variables.


Rough Logic: How much do the variables co-vary
Equivalent: How does one variable change when the other variable
changes.
Example: Household income and Average Health of the Household.
Lets say we find a positive correlation!

Lecture 1 ECO-2400 January 20, 2021 12 / 29


Introduction

Correlation continued

Common Interpretations:
Households that have higher income also have higher average health
Households that have higher health also have higher income
Better Income leads to better health
Better health leads to better income.

Lecture 1 ECO-2400 January 20, 2021 13 / 29


Introduction

Correlation continued

Conclusion:
Households that have higher income also have higher average health
Households that have higher health also have higher income

THESE ARE TRUE STATEMENTS BUT. . .


Better Income leads to better health
Better health leads to better income.
THESE STATEMENTS IMPLY -
Direction of Effect: Health to Income OR Income to Health

Lecture 1 ECO-2400 January 20, 2021 14 / 29


Introduction

Correlation continued

If I agree with, say “Better Income Leads to Better Health” Logical

Conclusion: If I transfer some money to households, I should see better


health!

YOU MAY BE COMPLETELY WRONG!

Lecture 1 ECO-2400 January 20, 2021 15 / 29


Introduction

Partial correlation

For example, Higher Income households may also be households with


better educated adult members and it may be education that drives health
and not income!

Logical Question: Does Income have an effect on Health after you take
into account education?

Partial correlation coefficient: Is a measure that takes into account the


effect of the “other factor(s)”.
It measures how much does income and health co-vary after you subtract
out the effect of education from each of them.
“Partial Out” the effect of education.

Lecture 1 ECO-2400 January 20, 2021 16 / 29


Introduction

Regression Analysis

Is an equivalent way of answering the same question.

It asks what is the effect of a change in one unit of income on health,


education kept constant “Education kept constant” IS ACTUALLY “the
effect of education partial-ed out!”

Lecture 1 ECO-2400 January 20, 2021 17 / 29


WooldridgeCh1

Lets start...

Economic model of crime


Aim: Modelling amount of time spent in criminal activity as a function of
its determinants
y = f (x1 , x2 , x3 , x4 , x5 , x6 , x7 ) (1)
where,
y = hours spent in criminal activities,
x1 = “wage” for an hour spent in criminal activity,
x2 = hourly wage in legal employment,
x3 = income other than from crime or employment,
x4 = probability of getting caught,
x5 = probability of being convicted if caught,
x6 = expected sentence if convicted, and
x7 = age.
Lecture 1 ECO-2400 January 20, 2021 18 / 29
WooldridgeCh1

Econometric Modelling

Economic model of crime


Aim: Modelling amount of time spent in criminal activity as a function of
its determinants
crime = β0 + β1 wagef + β2 otherinc + β3 arrestfreq+
(2)
β4 convictprob + β5 Avsentence + β6 age + µ
where,
crime = some measure of frequency of criminal activities,
wagef = wage from formal/legal employment,
otherinc = income from other sources - inheritance, unemployment
benefits,
arrestfreq = the frequency of arrests for prior infractions,
convictprob = the frequency of conviction, and,
Avsentence = the average sentence length after conviction,
age = age
Lecture 1 ECO-2400 January 20, 2021 19 / 29
WooldridgeCh1

Another example

Job training and worker productivity


Aim: To assess whether job training has an effect on worker productivity

wage = f (education, experience, training) (3)

where,
wage = hourly wage,
education = years of formal education,
experience = years of workforce experience, and
training = weeks spent in job training.

Lecture 1 ECO-2400 January 20, 2021 20 / 29


WooldridgeCh1

Econometric model

Job training and worker productivity


Aim: To assess whether job training has an effect on worker productivity

wage = β0 + β1 educ + β3 exper + β4 training + µ (4)

where,
wage = hourly wage,
education = years of formal education,
experience = years of workforce experience, and
training = weeks spent in job training.

Lecture 1 ECO-2400 January 20, 2021 21 / 29


WooldridgeCh1

Cross-sectional data

A cross-sectional data set consists of a sample of individuals, households,


firms, cities, states, countries, or a variety of other units, taken at a given
point in time.
obs wage exper training married
1 10 0 0 1
2 12 4 0 1
3 30 7 1 0
. . . . .
. . . . .
99 100 1.5 0 0
100 80 2 1 1

Lecture 1 ECO-2400 January 20, 2021 22 / 29


WooldridgeCh1

Time series data

A time series data set consists of observations on a variable or several


variables over time.
country year GDPrate Unemployment LeftGovt
A 1920 0.5 20 0
A 1921 -0.2 30 0
A 1921 -0.4 40 1
. . . . .
A 2018 0.7 20 1
A 2019 6.5 5 0
A 2020 2 10 0

Lecture 1 ECO-2400 January 20, 2021 23 / 29


WooldridgeCh1

Pooled cross-sectional data

A pooled cross sectional data set has both cross-sectional and time
components
country year GDPrate Unemployment LeftGovt
Australia 2013 0.5 20 0
Australia 2014 -0.2 30 0
Bangladesh 2013 -0.4 40 1
. . . . .
Germany 2013 0.7 20 1
Kenya 2013 6.5 5 0
Kenya 2014 2 10 0

Lecture 1 ECO-2400 January 20, 2021 24 / 29


WooldridgeCh1

Panel Data

A panel data set set consists of a time series for each cross-sectional
member in the data set.
country year GDPrate Unemployment LeftGovt
A 2013 0.5 20 0
A 2014 -0.2 30 0
A 2015 -0.4 40 1
. . . . .
B 2013 0.7 20 1
B 2014 6.5 5 0
B 2015 2 10 0

Lecture 1 ECO-2400 January 20, 2021 25 / 29


WooldridgeCh1

Let’s test our understanding now

Marks of all students in your class in compulsory subjects in semester


1.
Marks of all students in your class in compulsory subjects in semester
1 & 2.
Marks of all students in your class in elective subjects in semester 1 &
2.

Lecture 1 ECO-2400 January 20, 2021 26 / 29


WooldridgeCh1

Student Semester Subject1 Subject2


A 1 50 85
B 1 70 90

Student Semester Subject1 Subject2


A 1 50 85
A 2 90 60
B 1 70 90
B 2 60 45

Student Semester ElecSubject1 ElecSubject2


A 1 50 85
C 2 76 65
B 1 45 65
B 2 79 20
Lecture 1 ECO-2400 January 20, 2021 27 / 29
End

REMEMBER: Correlation does not IMPLY Causation

Lecture 1 ECO-2400 January 20, 2021 28 / 29


End

Lecture 1 ECO-2400 January 20, 2021 29 / 29

You might also like